© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64794
    Prev
    Next
    INDEX
    Explanations

    long term span or pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     убий
    -1.00
    ÁB
    -0.94
     dó
    -0.93
    畀
    -0.92
     خدمات
    -0.92
    esque
    -0.88
     maceta
    -0.87
     своим
    -0.84
    品種
    -0.84
     vivienda
    -0.83
    POSITIVE LOGITS
     www
    1.10
     http
    1.02
     https
    1.02
     Selasa
    1.00
     lul
    0.94
    www
    0.91
    lsz
    0.89
    ﺿ
    0.88
     Makanan
    0.88
    眼下
    0.88
    Activations Density 0.000%

    No Known Activations